import numpy as np
import pandas as pd

# Visualisation libraries

## Text
from colorama import Fore, Back, Style
from IPython.display import Image, display, Markdown, Latex, clear_output

## progressbar
import progressbar

## plotly
from plotly.offline import init_notebook_mode, iplot 
import plotly.graph_objs as go
import plotly.offline as py
from plotly.subplots import make_subplots
import plotly.express as px

## seaborn
import seaborn as sns

## matplotlib
import matplotlib.pyplot as plt
from matplotlib.patches import Ellipse, Polygon
from matplotlib.font_manager import FontProperties
import matplotlib.colors as mcolors
plt.style.use('seaborn-whitegrid')
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12
plt.rcParams['text.color'] = 'k'
%matplotlib inline

import warnings
warnings.filterwarnings("ignore")

Heart Disease Dataset

In this article, we analyze the Heart Disease Dataset from the UCI Machine Learning Repository.

Picture Source: harvard.edu

Attribute Information:

1. Age
2. Sex
   • 0: Female
   • 1: Male
3. Chest Pain Type
   • 1: Typical Angina
   • 2: Atypical Angina
   • 3: Non-Anginal Pain
   • 4: Asymptomatic

• Resting Blood Pressure

1. Serum Cholestoral (in mg/dl )
2. FBS: Fasting Blood Sugar > 120 mg/dl
   • 0 = False
   • 1 = True
3. Resting Electrocardiographic Results
   • 0: normal
   • 1: having ST-T wave abnormality (T wave inversions and/or ST elevation or depression of > 0.05 mV)
   • 2: showing probable or definite left ventricular hypertrophy by Estes' criteria
4. Maximum Heart Rate Achieved
5. Exercise Induced Angina
   • 0: No
   • 1: Yes
6. Oldpeak = St Depression Induced By Exercise Relative To Rest
7. Slope: The Slope Of The Peak Exercise ST Segment
   • 1: Upsloping
   • 2: Flat
   • 3: Downsloping
8. Number Of Major Vessels (0-3) Colored By Flourosopy
9. Thal
   • 3: Normal
   • 6: Fixed Defect
   • 7: Reversable Defect

Variable to be predicted

• Heart Disease
  • 0: Absence
  • 1: Presence

Problem Description

The object of the exercise is to develop a predictive model that can predict whether heart disease is present or absent based on the rest of the given features.

File = 'heart-disease/heart.dat'
Attributes = ['Age', 'Sex', 'Chest Pain Type', 'Resting Blood Pressure', 'Serum Cholestoral',
              'Fasting Blood Sugar', 'Resting Electrocardiographic Results', 'Maximum Heart Rate Achieved',
              'Exercise Induced Angina', 'Oldpeak', 'Slope', 'Number of Major Vessels', 'Thal', 'Heart Disease']
df = pd.DataFrame(data = np.genfromtxt(File, delimiter=' '), columns = Attributes)
#
Data = df.copy()
Temp = ['Sex', 'Chest Pain Type', 'Fasting Blood Sugar', 'Resting Electrocardiographic Results',
       'Exercise Induced Angina', 'Slope', 'Number of Major Vessels','Thal']
for c in Temp:
    Data[c] = Data[c].astype(int).astype(str)
del Temp, c
Target = 'Heart Disease'
Labels = ['Absent', 'Present']
Data['Heart Disease'] = (Data['Heart Disease']-1).astype(int).replace({0: Labels[0], 1: Labels[1]})
Data['Age'] = Data['Age'].astype(int)

def Data_info(Inp, Only_NaN = False):
    Out = Inp.dtypes.to_frame(name='Data Type').sort_values(by=['Data Type'])
    Out = Out.join(Inp.isnull().sum().to_frame(name = 'Number of NaN Values'), how='outer')
    Out ['Size'] = Inp.shape[0]
    Out['Percentage'] = 100 - np.round(100*(Out['Number of NaN Values']/Inp.shape[0]),2)
    Out.index.name = 'Features'
    Out['Data Type'] = Out['Data Type'].astype(str)
    if Only_NaN:
        Out = Out.loc[Out['Number of NaN Values']>0]
    return Out

# Maps
Maps = {'Sex': {'0':'Female', '1':'Male'},
        'Chest Pain Type': {'1':'Typical Angina', '2':'Atypical Angina', '3': 'Non-Anginal Pain', '4':'Asymptomatic'},
        'Fasting Blood Sugar': {'0': 'False', '1': 'True'}, 'Exercise Induced Angina': {'0': 'No', '1': 'Yes'},
        'Slope': {'1': 'Upsloping', '2': 'Flat', '3': 'Downsloping'},
        'Thal':  {'3': 'Normal', '6': 'Fixed Defect','7': 'Reversable Defect'}}

for c in list(Maps.keys()):
    Data[c] = Data[c].replace(Maps[c])
    
del c
display(Data)

#
display(pd.DataFrame({'Number of Instances': [Data.shape[0]], 'Number of Attributes': [Data.shape[1]]}).style.hide_index())

	Age	Sex	Chest Pain Type	Resting Blood Pressure	Serum Cholestoral	Fasting Blood Sugar	Resting Electrocardiographic Results	Maximum Heart Rate Achieved	Exercise Induced Angina	Oldpeak	Slope	Number of Major Vessels	Thal	Heart Disease
0	70	Male	Asymptomatic	130.0	322.0	False	2	109.0	No	2.4	Flat	3	Normal	Present
1	67	Female	Non-Anginal Pain	115.0	564.0	False	2	160.0	No	1.6	Flat	0	Reversable Defect	Absent
2	57	Male	Atypical Angina	124.0	261.0	False	0	141.0	No	0.3	Upsloping	0	Reversable Defect	Present
3	64	Male	Asymptomatic	128.0	263.0	False	0	105.0	Yes	0.2	Flat	1	Reversable Defect	Absent
4	74	Female	Atypical Angina	120.0	269.0	False	2	121.0	Yes	0.2	Upsloping	1	Normal	Absent
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
265	52	Male	Non-Anginal Pain	172.0	199.0	True	0	162.0	No	0.5	Upsloping	0	Reversable Defect	Absent
266	44	Male	Atypical Angina	120.0	263.0	False	0	173.0	No	0.0	Upsloping	0	Reversable Defect	Absent
267	56	Female	Atypical Angina	140.0	294.0	False	2	153.0	No	1.3	Flat	0	Normal	Absent
268	57	Male	Asymptomatic	140.0	192.0	False	0	148.0	No	0.4	Flat	0	Fixed Defect	Absent
269	67	Male	Asymptomatic	160.0	286.0	False	2	108.0	Yes	1.5	Flat	3	Normal	Present

270 rows × 14 columns

Number of Instances	Number of Attributes
270	14

def Data_Plot(Inp, W = False):
    data_info = Inp.copy()
    data_info = Inp.dtypes.astype(str).to_frame(name='Data Type')
    Temp = Inp.isnull().sum().to_frame(name = 'Number of NaN Values')
    data_info = data_info.join(Temp, how='outer')
    data_info ['Size'] = Inp.shape[0]
    data_info['Percentage'] = 100 - np.round(100*(data_info['Number of NaN Values']/Inp.shape[0]),2)
    data_info = data_info.reset_index(drop = False).rename(columns = {'index':'Features'})
    #
    fig = px.bar(data_info, x= 'Features', y= 'Percentage', color = 'Data Type', text = 'Data Type',
                color_discrete_sequence = ['PaleGreen', 'LightCyan', 'PeachPuff', 'Pink', 'Plum'],
                 hover_data = data_info.columns)
    fig.update_layout(plot_bgcolor= 'white', legend=dict(x=1.01, y=.5, traceorder="normal",
                                                         bordercolor="DarkGray", borderwidth=1))
    fig.update_traces(texttemplate= 6*' ' + '%{label}', textposition='inside')
    fig.update_traces(marker_line_color= 'Black', marker_line_width=1., opacity=1)
    if W:
        fig.update_layout(width = W)
    fig.update_layout(title={'text': '<b>' + 'Dataset Overview' + '<b>', 'x':0.5,
                             'y': 0.92, 'xanchor': 'center', 'yanchor': 'top'}, yaxis_title='Frequency')
    fig.show()
    return data_info
    
    
_ = Data_Plot(Data)

Exploratory Data Analysis

def DistPlot1(Feat, Target = Target, nbins = 20, Colors = ['LightSalmon', 'LightBlue'], LC = 'Black',
             yLim = [0, 80], H = 450, titleY = 0.92, Inp = Data):
    fig = px.histogram(Inp, x = Feat, nbins=nbins, color= Target, marginal= 'box',
                       color_discrete_sequence= Colors, hover_data=Data.columns)
    fig.update_xaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=False, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=False, gridwidth=1, gridcolor='Lightgray')
    fig.update_yaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=True, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray')

    Name = '%s Distribution by %s' % (Target, Feat)

    fig.update_layout(legend_orientation='v', plot_bgcolor= 'white', height= H, width= 980,
                     title={'text': '<b>' + Name + '<b>', 'x':0.5, 'y': titleY, 'xanchor': 'center', 'yanchor': 'top'},
                     yaxis_title='Frequency')
    fig.update_traces(marker_line_color= LC, marker_line_width=0.5, opacity=1)
    fig['layout']['yaxis'].update(range=yLim)
    fig.show()
    
def DispPlot2(Feat, ColorFeat, xLim, yLim, Target = Target, nbins = 5, titleY = 0.90, LC = 'Black', H2 = 320, W = 980, 
            Colors1 = ['Pink', 'BlueViolet'], Colors2 = ['OrangeRed', 'LimeGreen'], Inp = Data):
    # Top Figure
    fig = make_subplots(rows=1, cols=2, horizontal_spacing = 0.02, shared_yaxes=True,
                        subplot_titles=('%s: <b>%s<b>' % (Target,Labels[0]), '%s: <b>%s<b>' % (Target,Labels[1])))
    for j in range(2):
        Temp = Inp.loc[Inp[Target] == Labels[j]].sort_values(by = ColorFeat)
        if Colors1 == None:
            figtemp = px.histogram(Temp, x= Feat, color = ColorFeat, nbins = nbins)
        else:
            figtemp = px.histogram(Temp, x= Feat, color = ColorFeat, nbins = nbins,
                                color_discrete_sequence = Colors1)
        for i in range(len(figtemp['data'])):
                       fig.add_trace(figtemp['data'][i], row=1, col=j+1)
        del figtemp, Temp

    fig.update_traces(marker_line_color= LC, marker_line_width=1, opacity=1)
    fig.update_yaxes(title_text ='Frequency', row=1, col=1)
    fig.update_traces(showlegend = False, row=1, col=2)
    fig.update_xaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=False, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=False, gridwidth=1, gridcolor='Lightgray', range=xLim)
    fig.update_yaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=True, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray', range=yLim)
    fig.update_layout(plot_bgcolor= 'white', barmode='stack', width = W)
    Name = '%s Distribution by %s and %s' % (Feat, ColorFeat, Target)
    fig.update_layout(title={'text': '<b>' + Name + '<b>', 'x':0.5, 'y': titleY, 'xanchor': 'center', 'yanchor': 'top'})
    fig.show() 
    # Bottom Figure
    fig = px.box(Data, x= Feat,  y = ColorFeat, color = Target,
                   color_discrete_sequence= Colors2, hover_data=Data.columns)
    fig.update_traces(quartilemethod='linear')
    fig.update_xaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=False, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=False, gridwidth=1, gridcolor='Lightgray', range=xLim)
    fig.update_yaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=True, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray')
    fig.update_layout(plot_bgcolor= 'white', barmode='stack', height= H2, width = W)
    fig.show()

def Correlation_Plot (Inp, Fig_Size = 12, annot_kws = 11):
    Correlation_Matrix = Inp.corr().round(2)
    mask = np.zeros_like(Correlation_Matrix)
    mask[np.triu_indices_from(mask)] = True
    for i in range(len(mask)):
        mask[i,i]=0
    fig, ax = plt.subplots(figsize=(Fig_Size, Fig_Size))
    sns.heatmap(Correlation_Matrix, ax=ax, mask=mask, annot=True, square=True, 
                cmap =sns.color_palette("Greens", n_colors=10), linewidths = 0.2, vmin=0, vmax=1,
                cbar_kws={'label': 'Correlation', "aspect":30, "shrink": .4},  annot_kws={"size": annot_kws})
    return Correlation_Matrix

def Feature_Correlation(Inp, Target = Target, annot_kws = 11, FS = (17, 16), rep_long_labels = False):
    Fig, ax = plt.subplots(figsize = FS)
    Temp = Inp.corr().round(2)
    Temp = Temp.loc[(Temp.index == Target)].drop(columns = Target).T.sort_values(by = Target).T
    _ = sns.heatmap(Temp, ax=ax, annot=True, square=True,  cmap =sns.color_palette("YlGn", n_colors=Temp.shape[1]),
                    linewidths = 0.8, vmin=0, vmax=1,
                    annot_kws={"size": annot_kws},
                    cbar_kws={'label': 'Correlation with %s' % Target,
                              "aspect":40, "shrink": .4, "orientation": "horizontal"})
    if rep_long_labels:
        labels = [x.replace(' ','\n').replace('\nof\n',' of\n')
                  for x in [item.get_text() for item in ax.get_xticklabels()]]
        _ = ax.set_xticklabels(labels)
        _ = ax.set_yticklabels('')

Feature Correlation

_ = Correlation_Plot (df, 10)
# Feature_Correlation(df, annot_kws = 11, FS = (12, 16), rep_long_labels = True)

Age Distribution and Heart Disease

DispPlot2(Feat = 'Age', ColorFeat = 'Sex', xLim = [10, 90], yLim = [0, 60])

Resting Blood Pressure Distribution and Heart Disease

DispPlot2(Feat = 'Resting Blood Pressure', ColorFeat = 'Fasting Blood Sugar', xLim = [80, 200], yLim = [0, 40], nbins = 20)

Serum Cholestoral Distribution and Heart Disease

DispPlot2(Feat = 'Serum Cholestoral', ColorFeat = 'Fasting Blood Sugar', xLim = [0, 700], yLim = [0, 70], nbins = 10)

Maximum Heart Rate Achieved and Heart Disease

In this section, we demonstrate the relationship between the maximum heart rate achieved and heart disease.

DispPlot2(Feat = 'Maximum Heart Rate Achieved', ColorFeat = 'Chest Pain Type',
          Colors1 = ['Snow','MistyRose', 'Tomato', 'DarkRed'],
          xLim = [80, 230], yLim = [0, 40], nbins = 20, H2 = 450)

---

References

1. Detrano, R., Janosi, A., Steinbrunn, W., Pfisterer, M., Schmid, J.J., Sandhu, S., Guppy, K.H., Lee, S. and Froelicher, V., 1989. International application of a new probability algorithm for the diagnosis of coronary artery disease. The American journal of cardiology, 64(5), pp.304-310.

2. Aha, D. and Kibler, D., 1988. Instance-based prediction of heart-disease presence with the Cleveland database. University of California, 3(1), pp.3-2.

3. Gennari, J.H., Langley, P. and Fisher, D., 1989. Models of incremental concept formation. Artificial intelligence, 40(1-3), pp.11-61.

---